|
--- |
|
library_name: transformers |
|
base_model: openai/clip-vit-large-patch14-336 |
|
tags: |
|
- generated_from_trainer |
|
model-index: |
|
- name: clip-finetuned-csu-p14-336-e3l58-l |
|
results: [] |
|
--- |
|
|
|
<!-- This model card has been generated automatically according to the information the Trainer had access to. You |
|
should probably proofread and complete it, then remove this comment. --> |
|
|
|
# clip-finetuned-csu-p14-336-e3l58-l |
|
|
|
This model is a fine-tuned version of [openai/clip-vit-large-patch14-336](https://huggingface.co/openai/clip-vit-large-patch14-336) on an unknown dataset. |
|
It achieves the following results on the evaluation set: |
|
- Loss: 0.9259 |
|
|
|
## Model description |
|
|
|
More information needed |
|
|
|
## Intended uses & limitations |
|
|
|
More information needed |
|
|
|
## Training and evaluation data |
|
|
|
More information needed |
|
|
|
## Training procedure |
|
|
|
### Training hyperparameters |
|
|
|
The following hyperparameters were used during training: |
|
- learning_rate: 5e-08 |
|
- train_batch_size: 128 |
|
- eval_batch_size: 8 |
|
- seed: 42 |
|
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08 |
|
- lr_scheduler_type: linear |
|
- num_epochs: 3.0 |
|
|
|
### Training results |
|
|
|
| Training Loss | Epoch | Step | Validation Loss | |
|
|:-------------:|:------:|:-----:|:---------------:| |
|
| 0.3758 | 0.0921 | 500 | 1.4188 | |
|
| 0.4108 | 0.1842 | 1000 | 1.3514 | |
|
| 0.4335 | 0.2763 | 1500 | 1.2895 | |
|
| 0.3436 | 0.3685 | 2000 | 1.2415 | |
|
| 0.366 | 0.4606 | 2500 | 1.1949 | |
|
| 0.3191 | 0.5527 | 3000 | 1.1560 | |
|
| 0.2779 | 0.6448 | 3500 | 1.1234 | |
|
| 0.2942 | 0.7369 | 4000 | 1.0993 | |
|
| 0.2615 | 0.8290 | 4500 | 1.0805 | |
|
| 0.2715 | 0.9211 | 5000 | 1.0615 | |
|
| 0.2509 | 1.0133 | 5500 | 1.0462 | |
|
| 0.2653 | 1.1054 | 6000 | 1.0306 | |
|
| 0.2199 | 1.1975 | 6500 | 1.0183 | |
|
| 0.1844 | 1.2896 | 7000 | 1.0079 | |
|
| 0.2143 | 1.3817 | 7500 | 0.9970 | |
|
| 0.2011 | 1.4738 | 8000 | 0.9887 | |
|
| 0.1995 | 1.5660 | 8500 | 0.9807 | |
|
| 0.2493 | 1.6581 | 9000 | 0.9733 | |
|
| 0.2192 | 1.7502 | 9500 | 0.9669 | |
|
| 0.1882 | 1.8423 | 10000 | 0.9616 | |
|
| 0.2193 | 1.9344 | 10500 | 0.9551 | |
|
| 0.2148 | 2.0265 | 11000 | 0.9495 | |
|
| 0.1975 | 2.1186 | 11500 | 0.9449 | |
|
| 0.1791 | 2.2108 | 12000 | 0.9409 | |
|
| 0.2057 | 2.3029 | 12500 | 0.9382 | |
|
| 0.2037 | 2.3950 | 13000 | 0.9352 | |
|
| 0.2011 | 2.4871 | 13500 | 0.9318 | |
|
| 0.1551 | 2.5792 | 14000 | 0.9295 | |
|
| 0.1565 | 2.6713 | 14500 | 0.9279 | |
|
| 0.1963 | 2.7634 | 15000 | 0.9268 | |
|
| 0.1823 | 2.8556 | 15500 | 0.9262 | |
|
| 0.1854 | 2.9477 | 16000 | 0.9259 | |
|
|
|
|
|
### Framework versions |
|
|
|
- Transformers 4.45.0.dev0 |
|
- Pytorch 1.12.1 |
|
- Datasets 2.21.0 |
|
- Tokenizers 0.19.1 |
|
|
